Lila Sciences' AI lab screens 2,942 catalysts in 3 months, cracks green hydrogen's OER problem
tw_killian · x · 2026-09-25
Lila Sciences' AI-directed lab proposed, synthesized, and screened 2,942 catalysts in three months for acidic oxygen evolution reaction (OER) — the chemistry bottlenecking green hydrogen for 50 years — identifying 6 high-performing material families.
- Green hydrogen catalysts have long relied on iridium, one of Earth's rarest metals with only a few tonnes mined per year
- The AI surfaced a palladium-based lead the field had written off, now past 1,000 hours of testing in acid
- Electrochemist Ken Jenewein initially thought the model had gone astray after only a few learning cycles; two science leads with 40 years of combined materials experience also doubted it — until experiments confirmed the AI was right
- The result showcases an end-to-end workflow pairing domain experts with proactive AI models
More from Apps
- Qure.ai releases model that splits chest X-rays into bone, soft tissue and lungs — multimodalart · 2026-09-25
- Meta's Muse tops charts on distribution but faces a personal-agent retention problem — 4KTV · 2026-09-25
- Solo dev used AI to recreate North America's 1830-1900 railroad boom in a game — randal_olson · 2026-09-25
- How to Optimize AI Tool Budget Usage: User Seeks Strategies and Expert Resources — Previous-Display-593 · 2026-09-25
- G2 report: 41% of software buyers use deep research mode, diluting citations as AI visibility signal — sanderssays · 2026-09-25
- From technical drawings alone, Claude builds interactive smelting furnace in Blender — EricBuess · 2026-09-25